ResearchTasksDialogue Evaluation AlignmentFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedCRSArena-Eval KG (test)FACE0.543Pearson r (Turn-level Rel.)6Jun 15, 2026CRSArena-Eval RD (test)FACE0.549Pearson r (Turn-level Rel)6Jun 15, 2026